peft-lora-starcoderplus-chat-asst-A100-40GB-colab

This model is a fine-tuned version of bigcode/starcoderplus on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9217

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

• load_in_8bit: False
• load_in_4bit: True
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: nf4
• bnb_4bit_use_double_quant: True
• bnb_4bit_compute_dtype: bfloat16

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.982	0.3	203	0.9101
0.9379	1.3	406	0.9078
0.8899	2.3	609	0.9217

Framework versions

• PEFT 0.5.0.dev0
• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.0
• Tokenizers 0.13.3